Commit Graph

85 Commits

Author SHA1 Message Date
Dark-Alex-17 78e772f455 style: Applied formatting to MCP module 2026-02-20 15:28:21 -07:00
Dark-Alex-17 a7c97aedb7 feat: Improved MCP server spinup and spindown when switching contexts or settings in the REPL: Modify existing config rather than stopping all servers always and re-initializing if unnecessary 2026-02-20 14:36:34 -07:00
Dark-Alex-17 746f9e7b24 fix: Improved sub-agent stdout and stderr output for users to follow 2026-02-20 13:47:28 -07:00
Dark-Alex-17 369a4f0a89 fix: Inject agent variables into environment variables for global tool calls when invoked from agents to modify global tool behavior 2026-02-20 11:38:24 -07:00
Dark-Alex-17 e0aab6bd02 fix: Fixed a bug in the new supervisor and todo built-ins that was causing errors with OpenAI models 2026-02-18 14:52:57 -07:00
Dark-Alex-17 d619ad1d48 fix: Removed the now unnecessary is_stale_response that was breaking auto-continuing with parallel agents 2026-02-18 13:36:25 -07:00
Dark-Alex-17 5b147e07b3 style: Applied formatting to the function module 2026-02-18 13:20:18 -07:00
Dark-Alex-17 944ce441d8 build: Upgraded to the most recent version of rmcp 2026-02-18 12:28:52 -07:00
Dark-Alex-17 d912d44fb3 feat: Created a CodeRabbit-style code-reviewer agent 2026-02-18 12:16:59 -07:00
Dark-Alex-17 bf923cb296 fix: Bypassed enabled_tools for user interaction tools so if function calling is enabled at all, the LLM has access to the user interaction tools when in REPL mode 2026-02-18 11:25:25 -07:00
Dark-Alex-17 d9f737e1bf feat: Added configuration option in agents to indicate the timeout for user input before proceeding (defaults to 5 minutes) 2026-02-18 11:24:47 -07:00
Dark-Alex-17 59690d045e feat: Added support for sub-agents to escalate user interaction requests from any depth to the parent agents for user interactions 2026-02-18 11:06:15 -07:00
Dark-Alex-17 5d95acba53 feat: built-in user interaction tools to remove the need for the list/confirm/etc prompts in prompt tools and to enhance user interactions in Loki 2026-02-18 11:05:43 -07:00
Dark-Alex-17 d46225d2a9 fix: When parallel agents run, only write to stdout from the parent and only display the parent's throbber 2026-02-18 09:59:24 -07:00
Dark-Alex-17 3af30a0e62 refactor: Cleaned up some left-over implementation stubs 2026-02-18 09:13:39 -07:00
Dark-Alex-17 69eca4d96d fix: Forgot to implement support for failing a task and keep all dependents blocked 2026-02-18 09:13:11 -07:00
Dark-Alex-17 7b2e4a83c9 fix: Clean up orphaned sub-agents when the parent agent 2026-02-18 09:12:32 -07:00
Dark-Alex-17 4e170b069b fix: Forgot to automatically add the bidirectional communication back up to parent agents from sub-agents (i.e. need to be able to check inbox and send messages) 2026-02-17 16:11:35 -07:00
Dark-Alex-17 22c75fb578 feat: Added an agent configuration property that allows auto-injecting sub-agent spawning instructions (when using the built-in sub-agent spawning system) 2026-02-17 15:49:40 -07:00
Dark-Alex-17 11ab9eb6b8 feat: Auto-dispatch support of sub-agents and support for the teammate pattern between subagents 2026-02-17 15:18:27 -07:00
Dark-Alex-17 29b232f407 docs: Initial documentation cleanup of parallel agent MVP 2026-02-17 14:30:28 -07:00
Dark-Alex-17 53e8c920e5 fix: Agent delegation tools were not being passed into the {{__tools__}} placeholder so agents weren't delegating to subagents 2026-02-17 14:19:22 -07:00
Dark-Alex-17 78d19bed4d feat: Full passive task queue integration for parallelization of subagents 2026-02-17 13:42:53 -07:00
Dark-Alex-17 10f4160635 feat: Implemented initial scaffolding for built-in sub-agent spawning tool call operations 2026-02-17 11:48:31 -07:00
Dark-Alex-17 7622836e8b feat: Initial models for agent parallelization 2026-02-17 11:27:55 -07:00
Dark-Alex-17 02b7ed37f6 feat: Supported the injection of RAG sources into the prompt, not just via the .sources rag command in the REPL so models can directly reference the documents that supported their responses 2026-02-13 17:45:56 -07:00
Dark-Alex-17 088588231b docs: Updated todo-system docs 2026-02-13 15:13:37 -07:00
Dark-Alex-17 43b2bd937e fix: Improved continuation prompt to not make broad todo-items 2026-02-09 15:36:57 -07:00
Dark-Alex-17 a4326875ba fix: Allow auto-continuation to work in agents after a session is compressed and if there's still unfinish items in the to-do list 2026-02-09 15:21:39 -07:00
Dark-Alex-17 a6b0acc35d feat: Implemented a built-in task management system to help smaller LLMs complete larger multistep tasks and minimize context drift 2026-02-09 12:49:06 -07:00
Dark-Alex-17 cc7fcd0b5b feat: Improved tool and MCP invocation error handling by returning stderr to the model when it is available 2026-02-04 12:00:21 -07:00
Dark-Alex-17 02fe59b913 feat: Added variable interpolation for conversation starters in agents 2026-02-04 10:51:59 -07:00
Dark-Alex-17 2a2922760e feat: Implemented retry logic for failed tool invocations so the LLM can learn from the result and try again; Also implemented chain loop detection to prevent loops 2026-02-01 17:06:16 -07:00
Dark-Alex-17 a3793460fd fix: Claude tool calls work incorrectly when tool doesn't require any arguments or flags; would provide an empty JSON object or error on no args 2026-02-01 17:05:36 -07:00
Dark-Alex-17 e0927a04d9 feat: Added gemini-3-pro to the supported vertexai models 2026-01-30 19:03:41 -07:00
Dark-Alex-17 8665604bab Fixed some typos in tool call error messages 2026-01-30 12:25:57 -07:00
Dark-Alex-17 0710441650 fix: Fixed a bug where --agent-variable values were not being passed to the agents 2026-01-23 14:15:59 -07:00
Dark-Alex-17 20a76cee3e feat: Added support for thought-signatures for Gemini 3+ models 2026-01-21 15:11:55 -07:00
Dark-Alex-17 cb64785867 style: Cleaned up an anyhow error 2025-12-16 14:51:35 -07:00
Dark-Alex-17 86839188e0 style: Improved error message for un-fully configured MCP configuration 2025-12-13 13:37:01 -07:00
Dark-Alex-17 a733b9247a style: Applied formatting 2025-12-03 15:06:50 -07:00
Dark-Alex-17 7d0ce94907 feat: Improved MCP implementation to minimize the tokens needed to utilize it so it doesn't quickly overwhelm the token space for a given model 2025-12-03 12:12:51 -07:00
Dark-Alex-17 dbf7329e87 refactor: Updated to the most recent Rust version with 2024 syntax 2025-11-07 15:50:55 -07:00
Dark-Alex-17 b77bb6e200 refactor: Changed the name of the summary_prompt setting to summary_context_prompt 2025-11-07 11:13:58 -07:00
Dark-Alex-17 1fa3b4a600 refactor: Renamed summarize_prompt setting to summarization_prompt 2025-11-07 11:09:48 -07:00
Dark-Alex-17 99bd502f62 refactor: Renamed the compress_threshold setting to compression_threshold 2025-11-07 11:06:20 -07:00
Dark-Alex-17 25a271dc95 style: Applied formatting 2025-11-06 18:19:25 -07:00
Dark-Alex-17 5da8616518 feat: Added the agents directory to sysinfo output 2025-11-06 13:22:13 -07:00
Dark-Alex-17 29f7ebe559 Added environment variables for agents for the global_tools and mcp_servers settings 2025-11-06 12:16:36 -07:00
Dark-Alex-17 9474f4f322 feat: Added built-in macros 2025-11-05 16:28:56 -07:00